English
Related papers

Related papers: Natural Option Critic

200 papers

Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We…

Artificial Intelligence · Computer Science 2016-12-06 Pierre-Luc Bacon , Jean Harb , Doina Precup

Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically…

Machine Learning · Computer Science 2020-09-22 James Martens

Natural Gradient Descent, a second-degree optimization method motivated by the information geometry, makes use of the Fisher Information Matrix instead of the Hessian which is typically used. However, in many cases, the Fisher Information…

Machine Learning · Computer Science 2023-03-10 Rajesh Shrestha

Option-critic learning is a general-purpose reinforcement learning (RL) framework that aims to address the issue of long term credit assignment by leveraging temporal abstractions. However, when dealing with extended timescales, discounting…

Machine Learning · Computer Science 2019-11-21 Akshay Dharmavaram , Matthew Riemer , Shalabh Bhatnagar

We present on-line policy gradient algorithms for computing the locally optimal policy of a constrained, average cost, finite state Markov Decision Process. The stochastic approximation algorithms require estimation of the gradient of the…

Optimization and Control · Mathematics 2018-12-18 Vikram Krishnamurthy , Felisa Vazquez Abad

Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning. One popular approach for addressing this challenge is the options framework (Sutton et…

Machine Learning · Computer Science 2020-01-01 Matthew Riemer , Miao Liu , Gerald Tesauro

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an actor and a critic. We consider using various…

Machine Learning · Computer Science 2023-01-16 Zaiwei Chen , Siva Theja Maguluri

Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value…

Machine Learning · Statistics 2017-03-14 Yemi Okesanjo , Victor Kofia

Natural policy gradient methods are popular reinforcement learning methods that improve the stability of policy gradient methods by utilizing second-order approximations to precondition the gradient with the inverse of the…

Machine Learning · Computer Science 2022-10-12 Brennan Gebotys , Alexander Wong , David A. Clausi

The options framework is a popular approach for building temporally extended actions in reinforcement learning. In particular, the option-critic architecture provides general purpose policy gradient theorems for learning actions from…

Machine Learning · Computer Science 2020-02-07 Matthew Riemer , Ignacio Cases , Clemens Rosenbaum , Miao Liu , Gerald Tesauro

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, most policy gradient methods drop the discount factor from the state distribution and therefore do…

Machine Learning · Computer Science 2020-03-02 Chris Nota , Philip S. Thomas

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

Natural gradient descent, which preconditions a gradient descent update with the Fisher information matrix of the underlying statistical model, is a way to capture partial second-order information. Several highly visible works have…

Machine Learning · Computer Science 2020-06-09 Frederik Kunstner , Lukas Balles , Philipp Hennig

We propose a formalism for shared control, which is the problem of defining a policy that blends user control and autonomous control. The challenge posed by the shared autonomy system is to maintain user control authority while allowing the…

Robotics · Computer Science 2020-07-31 Yoojin Oh , Shao-Wen Wu , Marc Toussaint , Jim Mainprice

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

We analyze the convergence rate of the unregularized natural policy gradient algorithm with log-linear policy parametrizations in infinite-horizon discounted Markov decision processes. In the deterministic case, when the Q-value is known…

Machine Learning · Computer Science 2023-03-15 Carlo Alfano , Patrick Rebeschini

In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents. We propose an algorithm that focuses on the termination condition, as opposed to -- as is common --…

Artificial Intelligence · Computer Science 2019-02-27 Anna Harutyunyan , Will Dabney , Diana Borsa , Nicolas Heess , Remi Munos , Doina Precup
‹ Prev 1 2 3 10 Next ›